Re: Postgresql locks up server - no response at all

Thanks for the heads up, Kevin.  I'll revert system settings (BIOS
and the like -- we use a combo of BIOS-level serial console and FreeBSD
serial console in boot0/boot2/kernel) and give things a shot again.

I'm likely going to keep HTT/SMP off, however, since it's just a UP
box anyways.

I'll report back my findings (here in this thread) in a few days.

Again, thanks!

-- 
| Jeremy Chadwick                                 jdc at parodius.com |
| Parodius Networking                        http://www.parodius.com/ |
| UNIX Systems Administrator                   Mountain View, CA, USA |
| Making life hard for others since 1977.                             |

On Wed, Aug 04, 2004 at 01:49:15PM -0700, Kevin Oberman wrote:
> > Date: Wed, 4 Aug 2004 13:34:56 -0700
> > From: Jeremy Chadwick <freebsd_at_jdc.parodius.com>
> > Sender: owner-freebsd-current_at_freebsd.org
> > 
> > I've seen this with our SuperMicro SuperServer 5013C-T, running mysqld.
> > Please note that the server is "heavily loaded" (note the quotes); usually
> > a load of around 0.50 to 1.00 at all times, with mysqld being the top
> > process.  Server runs all latest -CURRENT builds.
> > 
> > Many people over in freebsd-threads mentioned this problem, and recommended
> > all sorts-of different workarounds.  I tried every one available to me,
> > except mucking with PREEMPTION (as I did not feel comfortable tinkering
> > with a random .h file on the box; seemed to be a kernel-related thing,
> > so I'd rather have just an "options" line for it -- I'm conditionally
> > lazy).
> 
> Please note that PREEMPTION is now NOT enabled in CURRENT. scottl
> changed that a day or two ago because of all of these lock-ups. He and
> Julian are listed as working to isolate the problem. Scott believes it's
> in the scheduler. It's not specific to either ULE or 4BSD.
> 
> So cvsup, rebuild the kernel and you should be fine.At least for a while.
> -- 
> R. Kevin Oberman, Network Engineer
> Energy Sciences Network (ESnet)
> Ernest O. Lawrence Berkeley National Laboratory (Berkeley Lab)
> E-mail: oberman_at_es.net			Phone: +1 510 486-8634